Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs and their use in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     would
    -0.54
     Would
    -0.45
    ↵
    -0.44
     catch
    -0.43
    Would
    -0.43
     zou
    -0.42
     WOULD
    -0.42
    ,
    -0.42
     ir
    -0.42
    ...
    -0.41
    POSITIVE LOGITS
     raiſ
    0.93
     pleaſure
    0.92
     purpoſe
    0.89
     itſelf
    0.88
     ainfi
    0.87
     wikipagina
    0.85
     deſt
    0.84
     myſelf
    0.84
    клопе
    0.83
     ſtate
    0.83
    Act Density 0.390%

    No Known Activations